From: Eric Biggers <ebiggers@kernel.org>
To: linux-crypto@vger.kernel.org, fsverity@lists.linux.dev,
dm-devel@lists.linux.dev
Cc: x86@kernel.org, linux-arm-kernel@lists.infradead.org,
Ard Biesheuvel <ardb@kernel.org>,
Sami Tolvanen <samitolvanen@google.com>,
Bart Van Assche <bvanassche@acm.org>,
Herbert Xu <herbert@gondor.apana.org.au>,
Alasdair Kergon <agk@redhat.com>,
Mike Snitzer <snitzer@kernel.org>,
Mikulas Patocka <mpatocka@redhat.com>
Subject: [PATCH v6 00/15] Optimize dm-verity and fsverity using multibuffer hashing
Date: Fri, 21 Jun 2024 09:59:07 -0700 [thread overview]
Message-ID: <20240621165922.77672-1-ebiggers@kernel.org> (raw)
On many modern CPUs, it is possible to compute the SHA-256 hash of two
equal-length messages in about the same time as a single message, if all
the instructions are interleaved. This is because each SHA-256 (and
also most other cryptographic hash functions) is inherently serialized
and therefore can't always take advantage of the CPU's full throughput.
An earlier attempt to support multibuffer hashing in Linux was based
around the ahash API. That approach had some major issues, as does the
alternative ahash-based approach proposed by Herbert (see my response at
https://lore.kernel.org/linux-crypto/20240610164258.GA3269@sol.localdomain/).
This patchset instead takes a much simpler approach of just adding a
synchronous API for hashing equal-length messages.
This works well for dm-verity and fsverity, which use Merkle trees and
therefore hash large numbers of equal-length messages.
This patchset is organized as follows:
- Patch 1-3 add crypto_shash_finup_mb() and tests for it.
- Patch 4-5 implement finup_mb on x86_64 and arm64, using an
interleaving factor of 2.
- Patch 6 adds multibuffer hashing support to fsverity.
- Patches 7-14 are cleanups and optimizations to dm-verity that prepare
the way for adding multibuffer hashing support. These don't depend on
any of the previous patches.
- Patch 15 adds multibuffer hashing support to dm-verity.
On CPUs that support multiple concurrent SHA-256's (all arm64 CPUs I
tested, and AMD Zen CPUs), raw SHA-256 hashing throughput increases by
70-98%, and the throughput of cold-cache reads from dm-verity and
fsverity increases by very roughly 35%.
Changed in v6:
- All patches: added Reviewed-by and Acked-by tags
- "crypto: testmgr - add tests for finup_mb": Whitespace fix
- "crypto: testmgr - generate power-of-2 lengths more often":
Fixed undefined behavior
- "fsverity: improve performance by using multibuffer hashing":
Simplified a comment
- "dm-verity: reduce scope of real and wanted digests":
Fixed mention of nonexistent function in commit message
- "dm-verity: improve performance by using multibuffer hashing":
Two small optimizations, and simplified a comment
Changed in v5:
- Reworked the dm-verity patches again. Split the preparation work
into separate patches, fixed two bugs, and added some new cleanups.
- Other small cleanups
Changed in v4:
- Reorganized the fsverity and dm-verity code to have a unified code
path for single-block vs. multi-block processing. For data blocks
they now use only crypto_shash_finup_mb().
Changed in v3:
- Change API from finup2x to finup_mb. It now takes arrays of data
buffer and output buffers, avoiding hardcoding 2x in the API.
Changed in v2:
- Rebase onto cryptodev/master
- Add more comments to assembly
- Reorganize some of the assembly slightly
- Fix the claimed throughput improvement on arm64
- Fix incorrect kunmap order in fs/verity/verify.c
- Adjust testmgr generation logic slightly
- Explicitly check for INT_MAX before casting unsigned int to int
- Mention SHA3 based parallel hashes
- Mention AVX512-based approach
Eric Biggers (15):
crypto: shash - add support for finup_mb
crypto: testmgr - generate power-of-2 lengths more often
crypto: testmgr - add tests for finup_mb
crypto: x86/sha256-ni - add support for finup_mb
crypto: arm64/sha256-ce - add support for finup_mb
fsverity: improve performance by using multibuffer hashing
dm-verity: move hash algorithm setup into its own function
dm-verity: move data hash mismatch handling into its own function
dm-verity: make real_digest and want_digest fixed-length
dm-verity: provide dma_alignment limit in io_hints
dm-verity: always "map" the data blocks
dm-verity: make verity_hash() take dm_verity_io instead of
ahash_request
dm-verity: hash blocks with shash import+finup when possible
dm-verity: reduce scope of real and wanted digests
dm-verity: improve performance by using multibuffer hashing
arch/arm64/crypto/sha2-ce-core.S | 281 +++++++++++++-
arch/arm64/crypto/sha2-ce-glue.c | 40 ++
arch/x86/crypto/sha256_ni_asm.S | 368 ++++++++++++++++++
arch/x86/crypto/sha256_ssse3_glue.c | 39 ++
crypto/shash.c | 58 +++
crypto/testmgr.c | 89 ++++-
drivers/md/dm-verity-fec.c | 49 +--
drivers/md/dm-verity-fec.h | 9 +-
drivers/md/dm-verity-target.c | 581 ++++++++++++++++------------
drivers/md/dm-verity.h | 65 ++--
fs/verity/fsverity_private.h | 7 +
fs/verity/hash_algs.c | 8 +-
fs/verity/verify.c | 169 ++++++--
include/crypto/hash.h | 52 ++-
14 files changed, 1436 insertions(+), 379 deletions(-)
base-commit: ff33c2e6af99afcac3024a5c3ec8730d1e6b8ac7
--
2.45.2
next reply other threads:[~2024-06-21 17:00 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-06-21 16:59 Eric Biggers [this message]
2024-06-21 16:59 ` [PATCH v6 01/15] crypto: shash - add support for finup_mb Eric Biggers
2024-06-28 0:52 ` Herbert Xu
2024-06-21 16:59 ` [PATCH v6 02/15] crypto: testmgr - generate power-of-2 lengths more often Eric Biggers
2024-06-21 16:59 ` [PATCH v6 03/15] crypto: testmgr - add tests for finup_mb Eric Biggers
2024-06-21 16:59 ` [PATCH v6 04/15] crypto: x86/sha256-ni - add support " Eric Biggers
2024-06-21 16:59 ` [PATCH v6 05/15] crypto: arm64/sha256-ce " Eric Biggers
2024-06-21 16:59 ` [PATCH v6 06/15] fsverity: improve performance by using multibuffer hashing Eric Biggers
2024-06-21 16:59 ` [PATCH v6 07/15] dm-verity: move hash algorithm setup into its own function Eric Biggers
2024-06-21 16:59 ` [PATCH v6 08/15] dm-verity: move data hash mismatch handling " Eric Biggers
2024-06-21 16:59 ` [PATCH v6 09/15] dm-verity: make real_digest and want_digest fixed-length Eric Biggers
2024-06-21 16:59 ` [PATCH v6 10/15] dm-verity: provide dma_alignment limit in io_hints Eric Biggers
2024-06-21 16:59 ` [PATCH v6 11/15] dm-verity: always "map" the data blocks Eric Biggers
2024-06-21 16:59 ` [PATCH v6 12/15] dm-verity: make verity_hash() take dm_verity_io instead of ahash_request Eric Biggers
2024-06-21 16:59 ` [PATCH v6 13/15] dm-verity: hash blocks with shash import+finup when possible Eric Biggers
2024-06-21 16:59 ` [PATCH v6 14/15] dm-verity: reduce scope of real and wanted digests Eric Biggers
2024-06-21 16:59 ` [PATCH v6 15/15] dm-verity: improve performance by using multibuffer hashing Eric Biggers
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240621165922.77672-1-ebiggers@kernel.org \
--to=ebiggers@kernel.org \
--cc=agk@redhat.com \
--cc=ardb@kernel.org \
--cc=bvanassche@acm.org \
--cc=dm-devel@lists.linux.dev \
--cc=fsverity@lists.linux.dev \
--cc=herbert@gondor.apana.org.au \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-crypto@vger.kernel.org \
--cc=mpatocka@redhat.com \
--cc=samitolvanen@google.com \
--cc=snitzer@kernel.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).